Tests entity expansion of three legal character references, which each expand to a Unicode surrogate pair.
<!DOCTYPE doc [ <!ENTITY e "𐀀􏿽"> <!ELEMENT doc (#PCDATA)> ]> <doc>&e;</doc>
| Expected result | Actual result for org.apache.crimson.parser.XMLReaderImpl |
|---|---|
<?xml version="1.0" encoding="UTF-8"?>
<ConformanceResults>
<startDocument/>
<startElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
<attributes/>
</startElement>
<char>\uD800</char>
<char>\uDC00</char>
<char>\uDBFF</char>
<char>\uDFFD</char>
<char>\uDBFF</char>
<char>\uDFFF</char>
<endElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
</endElement>
<endDocument/>
</ConformanceResults>
| <?xml version="1.0" encoding="UTF-8"?>
<ConformanceResults>
<startDocument/>
<startElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
<attributes/>
</startElement>
<char>\uD800</char>
<char>\uDC00</char>
<char>\uDBFF</char>
<char>\uDFFD</char>
<char>\uDBFF</char>
<char>\uDFFF</char>
<endElement>
<namespaceURI/>
<localName>doc</localName>
<qualifiedName>doc</qualifiedName>
</endElement>
<endDocument/>
</ConformanceResults>
|